Table 3 Performance of the logistic regression, elastic net, and XGBoost algorithms across the eight MERP categories.

			Logistic regression							ElasticNetCV							XGBoost
MERP Category	# of true positives (training)	# of true positives (testing)	Precision	Recall	Specificity	F1	AUCROC	PR-ROC	Accuracy	Precision	Recall	Specificity	F1	AUCROC	PR-ROC	Accuracy	Precision	Recall	Specificity	F1	AUCROC	PR-ROC	Accuracy
Wrong Drug	1371	611	0.88	0.81	0.87	0.84	0.92	0.91	0.84	0.86	0.89	0.88	0.87	0.92	0.92	0.86	0.92	0.91	0.91	0.92	0.95	0.94	0.91
Wrong Time	1170	507	0.70	0.67	0.77	0.68	0.82	0.77	0.73	0.71	0.57	0.74	0.63	0.80	0.74	0.71	0.72	0.74	0.78	0.73	0.83	0.75	0.76
Wrong Strength or Concentration	1007	446	0.73	0.56	0.87	0.63	0.82	0.74	0.75	0.71	0.59	0.84	0.64	0.86	0.73	0.75	0.71	0.66	0.83	0.68	0.83	0.75	0.76
Wrong Dosage Form or Technique or Route	759	348	0.95	0.58	0.99	0.72	0.90	0.86	0.87	0.90	0.66	0.98	0.76	0.90	0.86	0.88	0.95	0.79	0.98	0.86	0.93	0.90	0.92
Improper Dose/Dose Omission	765	337	0.90	0.50	0.98	0.64	0.91	0.82	0.84	0.85	0.62	0.98	0.71	0.91	0.85	0.86	0.92	0.95	0.95	0.84	0.95	0.90	0.91
Wrong Rate	219	104	0.91	0.31	1.00	0.46	0.96	0.74	0.94	0.86	0.42	1.00	0.57	0.96	0.76	0.94	0.87	0.63	0.99	0.73	0.95	0.82	0.96
Wrong Patient	104	48	1.00	0.04	1.00	0.08	0.94	0.56	0.96	0.80	0.08	1.00	0.15	0.94	0.55	0.96	0.89	0.35	1.00	0.51	0.91	0.54	0.97
Monitoring Error	99	45	0.86	0.13	1.00	0.23	0.84	0.42	0.97	0.91	0.22	1.00	0.36	0.84	0.40	0.97	0.89	0.36	1.00	0.51	0.84	0.49	0.97

Quick links

Search